Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5484 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.2413. Min Range: -8.2413

Max Act: 8.2413. Min Act: -0.0000

Data Index: 881641 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 8.2413. Min Range: -8.2413

Max Act: 7.6488. Min Act: -0.0000

Data Index: 1247346 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 8.2413. Min Range: -8.2413

Max Act: 7.8631. Min Act: -0.0000

Data Index: 808750 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 8.2413. Min Range: -8.2413

Max Act: 7.6901. Min Act: -0.0000

Data Index: 971239 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.8448. Min Act: -0.0000

Data Index: 1178891 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.5230. Min Act: -0.0000

Data Index: 357605 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.6912. Min Act: -0.0000

Data Index: 485480 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.6545. Min Act: -0.0000

Data Index: 1318575 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.5092. Min Act: -0.0000

Data Index: 295072 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.6964. Min Act: -0.0000

Data Index: 757340 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.6100. Min Act: -0.0000

Data Index: 297279 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.4829. Min Act: -0.0000

Data Index: 971677 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.4023. Min Act: -0.0000

Data Index: 450324 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.1921. Min Act: -0.0000

Data Index: 388520 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.4106. Min Act: -0.0000

Data Index: 807235 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.5611. Min Act: -0.0000

Data Index: 1087626 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 8.2413. Min Range: -8.2413

Max Act: 6.6094. Min Act: -0.0000

Data Index: 619369 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 8.2413. Min Range: -8.2413

Max Act: 5.8285. Min Act: -0.0000

Data Index: 1191291 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 8.2413. Min Range: -8.2413

Max Act: 5.9963. Min Act: -0.0000

Data Index: 366621 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 8.2413. Min Range: -8.2413

Max Act: 5.9235. Min Act: -0.0000

Data Index: 1271 (C4 (Web Text))

Max Activating Token Index: 620